Feasibility of GPT-3 and GPT-4 for in-Depth Patient Education Prior to Interventional Radiological Procedures: A Comparative Analysis
CardioVascular and Interventional Radiology · 2024-02 · 47 (2) · 245-250
DOI: 10.1007/s00270-023-03563-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift CardioVascular and Interventional Radiology, online erschienen am 23.10.2023. Verfasst von Michael Scheschenja und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostic and Interventional Radiology, University Hospital Marburg, Philipps-University of Marburg, Baldingerstrasse 1, 35043, Marbur…. Hauptthemen laut MEDLINE: Radiology, Interventional, Patient Education as Topic. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Philipps-Universität Marburg.
Abstract (Originalsprache)
Purpose
This study explores the utility of the large language models, GPT-3 and GPT-4, for in-depth patient education prior to interventional radiology procedures. Further, differences in answer accuracy between the models were assessed. Materials and methods A total of 133 questions related to three specific interventional radiology procedures (Port implantation, PTA and TACE) covering general information as well as preparation details, risks and complications and post procedural aftercare were compiled. Responses of GPT-3 and GPT-4 were assessed for their accuracy by two board-certified radiologists using a 5-point Likert scale. The performance difference between GPT-3 and GPT-4 was analyzed.
Results
Both GPT-3 and GPT-4 responded with (5) “completely correct” (4) “very good” answers for the majority of questions ((5) 30.8% + (4) 48.1% for GPT-3 and (5) 35.3% + (4) 47.4% for GPT-4). GPT-3 and GPT-4 provided (3) “acceptable” responses 15.8% and 15.0% of the time, respectively. GPT-3 provided (2) “mostly incorrect” responses in 5.3% of instances, while GPT-4 had a lower rate of such occurrences, at just 2.3%. No response was identified as potentially harmful. GPT-4 was found to give significantly more accurate responses than GPT-3 ( p = 0.043).
Conclusion
GPT-3 and GPT-4 emerge as relatively safe and accurate tools for patient education in interventional radiology. GPT-4 showed a slightly better performance. The feasibility and accuracy of these models suggest their promising role in revolutionizing patient care. Still, users need to be aware of possible limitations. Graphical Abstract
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Diagnostic and Interventional Radiology, University Hospital Marburg, Philipps-University of Marburg, Baldingerstrasse 1, 35043, Marburg, DE, Germany. Michael.Scheschenja@med.uni-marburg.de.
- Department of Diagnostic and Interventional Radiology, University Hospital Marburg, Philipps-University of Marburg, Baldingerstrasse 1, 35043, Marburg, DE, Germany.
Förderung
- Philipps-Universität Marburg
Zitieren
APA
Scheschenja, M., Viniol, S., Bastian, M. B., Wessendorf, J., König, A. M., & Mahnken, A. H. (2024). Feasibility of GPT-3 and GPT-4 for in-Depth Patient Education Prior to Interventional Radiological Procedures: A Comparative Analysis. CardioVascular and Interventional Radiology, 47(2), 245-250. https://doi.org/10.1007/s00270-023-03563-2
Vancouver
Scheschenja M, Viniol S, Bastian MB, Wessendorf J, König AM, Mahnken AH. Feasibility of GPT-3 and GPT-4 for in-Depth Patient Education Prior to Interventional Radiological Procedures: A Comparative Analysis. CardioVascular and Interventional Radiology. 2024;47(2):245-250. doi:10.1007/s00270-023-03563-2
BibTeX
@article{Scheschenja2024,
author = {Scheschenja, Michael and Viniol, Simon and Bastian, Moritz B and Wessendorf, Joel and König, Alexander M and Mahnken, Andreas H},
title = {Feasibility of GPT-3 and GPT-4 for in-Depth Patient Education Prior to Interventional Radiological Procedures: A Comparative Analysis},
journal = {CardioVascular and Interventional Radiology},
year = {2024},
volume = {47},
number = {2},
pages = {245--250},
doi = {10.1007/s00270-023-03563-2}
}
EUVIMED